© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 84530
    Prev
    Next
    INDEX
    Explanations

    hydroponics and indoor gardens

    np_acts-logits-general · gemini-2.5-flash-lite

    words related to plant cultivation, particularly hydroponic growing systems and gardening.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron strongly activates on mentions of hydroponically grown plants or hydroponic cultivation.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     سگ
    -0.70
    GEBURTSDATUM
    -0.70
    Extern
    -0.69
    σεις
    -0.69
    jev
    -0.66
    TKey
    -0.65
    orme
    -0.65
    ặn
    -0.65
    pud
    -0.64
     آزمون
    -0.64
    POSITIVE LOGITS
     hydropon
    2.39
     Hydro
    1.87
     vertical
    1.78
    Hydro
    1.73
     aerop
    1.66
     indoor
    1.65
    hydro
    1.63
     vertik
    1.61
    Vertical
    1.59
     Vertical
    1.59
    Activations Density 0.045%

    No Known Activations